Metasearch MCP

🚀 Meta Search MCP Server

A MCP server for meta-search

🚀 Quick Start

This is a meta-search MCP server that uses the Tavily API to perform searches based on specified queries.

✨ Features

Components

This server uses the Tavily API to perform searches based on specified queries.

• Search results are returned in text format.
• Search results include AI responses, URIs, and search result titles.

Tools

This server implements the following tools:

• search: Performs a search based on the specified query
  • Required parameter: "query"
  • Optional parameter: "search_depth" (basic or advanced)

📦 Installation

1. Download the repository.

git clone https://github.com/YeonwooSung/metasearch-mcp.git

2. Open the Claude Desktop configuration file.

On MacOS: `~/Library/Application\ 支持/Claude/claude_desktop_config.json`
On Windows: `C:\Users\[username]\AppData\Roaming\Claude\claude_desktop_config.json`

3. Edit the configuration file as follows:

"mcpServers": {
  "tavily-search": {
    "command": "uv",
    "args": [
      "--directory",
      "C:\\your_path\\mcp-server-tavily",
      "run",
      "tavily-search"
    ],
    "env": {
      "TAVILY_API_KEY": "YOUR_TAVILY_API_KEY",
      "PYTHONIOENCODING": "utf-8"
    }
  }
}

4. Restart Claude Desktop.

💻 Usage Examples

Basic Usage

In Claude Desktop, when you request "Please search for something", you will receive search results.

Search example:

Please search in detail for today's events in Kamakura.

Response example:

According to the search results, today is December 1st. Here are the events starting on this day:
"Kamakura Promotion Photo Contest 2025"
Time: From December 1st, 2024, to January 31st, 2025
A photo contest for those who love Kamakura.
Applications are now being accepted.
In addition, the following upcoming related event:
On December 7th, 12 Kamakura artists will hold an exhibition at the Seibu Press Inn Kamakura Ofuna Station East Exit Lounge.

📚 Documentation

Log Storage Location

Logs are stored in the following locations:

For Windows:

C:\Users\[username]\AppData\Roaming\Claude\logs\mcp-server-tavily-search

Execution with Cursor

1. Create a shell script (e.g., script.sh) as follows:

#!/bin/bash
TARGET_DIR=/path/to/mcp-server-tavily
cd "${TARGET_DIR}"
export TAVILY_API_KEY="your-api-key"
export PYTHONIOENCODING=utf-8
uv --directory $PWD run tavily-search

2. Configure Cursor's MCP server settings as follows:

# Execute the following commands in the terminal to run the server and client
# Start the server
uvicorn tavily_search.asgi:application --reload
# Start the client
python -m pip install python-multipart
python -m fastapi start-server

3. Add the following content to Cursor's settings.json file:

{
    "mcp": {
        "servers": [
            {
                "name": "tavily-search",
                "host": "http://localhost:8000"
            }
        ]
    }
}

Execution with Docker Compose

1. Create a docker-compose.yml file in the project root directory and add the following content:

version: '3'
services:
  mcp-server:
    build:
      context: .
      dockerfile: Dockerfile
    ports:
      - "8000:8000"
    environment:
      - TAVILY_API_KEY=your-api-key
  mcp-client:
    image: fastapi
    command: start-server
    depends_on:
      - mcp-server

2. Execute the following commands in the terminal to build and run the services:

docker-compose build
docker-compose up

3. Add the following content to Cursor's settings.json file:

{
    "mcp": {
        "servers": [
            {
                "name": "tavily-search",
                "host": "http://localhost:8000"
            }
        ]
    }
}

4. Execute the following commands in the terminal to run the server and client:

uvicorn tavily_search.asgi:application --reload
python -m pip install python-multipart
python -m fastapi start-server